A fast and robust super-resolved binarization algorithm for license plate recognition

In this paper, we propose a fast and robust super-resolved binarization algorithm for license plate recognition. The quality of images acquired in outdoor conditions is usually degraded by factors such as low resolution, anti aliasing, and blurring. The proposed method, which is based on a binarization algorithm (FAIR: a Fast Algorithm for document Image Restoration) developed for the case of a simple image, computes the super resolution of the likelihood of text instead of the gray value of pixels. The algorithm can be considered as parameter free and is based on a rough localization of text in order to save computation time. Experimental results on several image sequences presenting a background noise and variation in contrast and illumination show the effectiveness of the method.